In this paper, we present a new approach to the fusion of Sentinel 1 (S1) and Sentinel 2 (S2) data for land cover mapping. The proposed solution aims at improving methods based on Sentinel 2 data, that are unusable in case of cloud cover. This goal is achieved by using S1 data to generate S2-like segmentation maps to be used to integrate S2 acquisitions forbidden by cloud cover. In particular, we propose for the first time in remote sensing a multi-temporal W-Net approach for the segmentation of Interferometric Wide swath mode (IW) Sentinel-1 data collected along ascending/descending orbit to discriminate rice, water, and bare soil. The quantitative assessment of segmentation accuracy shows an improvement of 0.18 and 0.25 in terms of accuracy and F1-score by applying the proposed multi-temporal procedure with respect to the previous single-date approach. Advantages and disadvantages of the proposed W-Net based solution have been tested in the National Park of Albufera, Valencia, and we show a performance gain in terms of the classical metrics used in segmentation tasks and the computational time.

No abstract

Remote Sensing applications can benefit from a relatively fine spatial resolution multispectral (MS) images and a high revisit frequency ensured by the twin satellites Sentinel-2. Unfortunately, only four out of thirteen bands are provided at the highest resolution of 10 meters, and the others at 20 or 60 meters. For instance the Short-Wave Infrared (SWIR) bands, provided at 20 meters, are very useful to detect active fires. Aiming to a more detailed Active Fire Detection (AFD) maps, we propose a super-resolution data fusion method based on Convolutional Neural Network (CNN) to move towards the 10-m spatial resolution the SWIR bands. The proposed CNN-based solution achieves better results than alternative methods in terms of some accuracy metrics. Moreover we test the super-resolved bands from an application point of view by monitoring active fire through classic indices. Advantages and limits of our proposed approach are validated on specific geographical area (the mount Vesuvius, close to Naples) that was damaged by widespread fires during the summer of 2017.

Kinematic characterization of a landslide at large, small, and detailed scale is today still rare and challenging, especially for long periods, due to the difficulty in implementing demanding ground surveys with adequate spatiotemporal coverage. In this work, the suitability of space-borne synthetic aperture radar sub-pixel offset tracking for the long-term monitoring of the Slumgullion landslide in Colorado (US) is investigated. This landslide is classified as a debris slide and has so far been monitored through ground surveys and, more recently, airborne remote sensing, while satellite images are scarcely exploited. The peculiarity of this landslide is that it is subject to displacements of several meters per year. Therefore, it cannot be monitored with traditional synthetic aperture radar differential interferometry, as this technique has limitations related to the loss of interferometric coherence and to the maximum observable displacement gradient/rate. In order to overcome these limitations, space-borne synthetic aperture radar sub-pixel offset tracking is applied to pairs of images acquired with a time span of one year between August 2011 and August 2013. The obtained results are compared with those available in the literature, both at landslide scale, retrieved through field surveys, and at point scale, using airborne synthetic aperture radar imaging and GPS. The comparison showed full congruence with the past literature. A consistency check covering the full observation period is also implemented to confirm the reliability of the technique, which results in a cheap and effective methodology for the long-term monitoring of large landslide-induced movements.

No abstract